A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species
Species identification—of importance for most biological disciplines—is not always straightforward as cryptic species hamper traditional identification. Fibre-optic near-infrared spectroscopy (NIRS) is a rapid and inexpensive method of use in various applications, including the identification of spe...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2015-09-01
|
Series: | PeerJ |
Subjects: | |
Online Access: | https://peerj.com/articles/991.pdf |
id |
doaj-e8a016bfeecc4745834b80a4c3c9d9f0 |
---|---|
record_format |
Article |
spelling |
doaj-e8a016bfeecc4745834b80a4c3c9d9f02020-11-25T01:08:14ZengPeerJ Inc.PeerJ2167-83592015-09-013e99110.7717/peerj.991A near-infrared spectroscopy routine for unambiguous identification of cryptic ant speciesMartin-Carl Kinzner0Herbert C. Wagner1Andrea Peskoller2Karl Moder3Floyd E. Dowell4Wolfgang Arthofer5Birgit C. Schlick-Steiner6Florian M. Steiner7Molecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaMolecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaMolecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaInstitute of Applied Statistics and Computing, University of Natural Resources and Life Sciences, Vienna, AustriaAgricultural Research Service, United States Department of Agriculture, Manhattan, KS, USAMolecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaMolecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaMolecular Ecology Group, Institute of Ecology, University of Innsbruck, Innsbruck, AustriaSpecies identification—of importance for most biological disciplines—is not always straightforward as cryptic species hamper traditional identification. Fibre-optic near-infrared spectroscopy (NIRS) is a rapid and inexpensive method of use in various applications, including the identification of species. Despite its efficiency, NIRS has never been tested on a group of more than two cryptic species, and a working routine is still missing. Hence, we tested if the four morphologically highly similar, but genetically distinct ant species Tetramorium alpestre, T. caespitum, T. impurum, and T. sp. B, all four co-occurring above 1,300 m above sea level in the Alps, can be identified unambiguously using NIRS. Furthermore, we evaluated which of our implementations of the three analysis approaches, partial least squares regression (PLS), artificial neural networks (ANN), and random forests (RF), is most efficient in species identification with our data set. We opted for a 100% classification certainty, i.e., a residual risk of misidentification of zero within the available data, at the cost of excluding specimens from identification. Additionally, we examined which strategy among our implementations, one-vs-all, i.e., one species compared with the pooled set of the remaining species, or binary-decision strategies, worked best with our data to reduce a multi-class system to a two-class system, as is necessary for PLS. Our NIRS identification routine, based on a 100% identification certainty, was successful with up to 66.7% of unambiguously identified specimens of a species. In detail, PLS scored best over all species (36.7% of specimens), while RF was much less effective (10.0%) and ANN failed completely (0.0%) with our data and our implementations of the analyses. Moreover, we showed that the one-vs-all strategy is the only acceptable option to reduce multi-class systems because of a minimum expenditure of time. We emphasise our classification routine using fibre-optic NIRS in combination with PLS and the one-vs-all strategy as a highly efficient pre-screening identification method for cryptic ant species and possibly beyond.https://peerj.com/articles/991.pdfCryptic-species complexAntsFormicidaeNeural networksOne-vs-all strategyPartial least squares regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Martin-Carl Kinzner Herbert C. Wagner Andrea Peskoller Karl Moder Floyd E. Dowell Wolfgang Arthofer Birgit C. Schlick-Steiner Florian M. Steiner |
spellingShingle |
Martin-Carl Kinzner Herbert C. Wagner Andrea Peskoller Karl Moder Floyd E. Dowell Wolfgang Arthofer Birgit C. Schlick-Steiner Florian M. Steiner A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species PeerJ Cryptic-species complex Ants Formicidae Neural networks One-vs-all strategy Partial least squares regression |
author_facet |
Martin-Carl Kinzner Herbert C. Wagner Andrea Peskoller Karl Moder Floyd E. Dowell Wolfgang Arthofer Birgit C. Schlick-Steiner Florian M. Steiner |
author_sort |
Martin-Carl Kinzner |
title |
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
title_short |
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
title_full |
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
title_fullStr |
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
title_full_unstemmed |
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
title_sort |
near-infrared spectroscopy routine for unambiguous identification of cryptic ant species |
publisher |
PeerJ Inc. |
series |
PeerJ |
issn |
2167-8359 |
publishDate |
2015-09-01 |
description |
Species identification—of importance for most biological disciplines—is not always straightforward as cryptic species hamper traditional identification. Fibre-optic near-infrared spectroscopy (NIRS) is a rapid and inexpensive method of use in various applications, including the identification of species. Despite its efficiency, NIRS has never been tested on a group of more than two cryptic species, and a working routine is still missing. Hence, we tested if the four morphologically highly similar, but genetically distinct ant species Tetramorium alpestre, T. caespitum, T. impurum, and T. sp. B, all four co-occurring above 1,300 m above sea level in the Alps, can be identified unambiguously using NIRS. Furthermore, we evaluated which of our implementations of the three analysis approaches, partial least squares regression (PLS), artificial neural networks (ANN), and random forests (RF), is most efficient in species identification with our data set. We opted for a 100% classification certainty, i.e., a residual risk of misidentification of zero within the available data, at the cost of excluding specimens from identification. Additionally, we examined which strategy among our implementations, one-vs-all, i.e., one species compared with the pooled set of the remaining species, or binary-decision strategies, worked best with our data to reduce a multi-class system to a two-class system, as is necessary for PLS. Our NIRS identification routine, based on a 100% identification certainty, was successful with up to 66.7% of unambiguously identified specimens of a species. In detail, PLS scored best over all species (36.7% of specimens), while RF was much less effective (10.0%) and ANN failed completely (0.0%) with our data and our implementations of the analyses. Moreover, we showed that the one-vs-all strategy is the only acceptable option to reduce multi-class systems because of a minimum expenditure of time. We emphasise our classification routine using fibre-optic NIRS in combination with PLS and the one-vs-all strategy as a highly efficient pre-screening identification method for cryptic ant species and possibly beyond. |
topic |
Cryptic-species complex Ants Formicidae Neural networks One-vs-all strategy Partial least squares regression |
url |
https://peerj.com/articles/991.pdf |
work_keys_str_mv |
AT martincarlkinzner anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT herbertcwagner anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT andreapeskoller anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT karlmoder anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT floydedowell anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT wolfgangarthofer anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT birgitcschlicksteiner anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT florianmsteiner anearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT martincarlkinzner nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT herbertcwagner nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT andreapeskoller nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT karlmoder nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT floydedowell nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT wolfgangarthofer nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT birgitcschlicksteiner nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies AT florianmsteiner nearinfraredspectroscopyroutineforunambiguousidentificationofcrypticantspecies |
_version_ |
1725183593723985920 |